© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 645
    Prev
    Next
    INDEX
    Explanations

    ethical, safe, or harmful prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ان
    1.59
    ن
    1.49
    न
    1.43
    ل
    1.36
    на
    1.29
    ور
    1.28
    ak
    1.16
    ной
    1.13
    ва
    1.11
    ే
    1.11
    POSITIVE LOGITS
    s
    1.04
    '
    1.00
    ς
    0.96
     MyDB
    0.94
     koska
    0.94
     Comme
    0.94
     muita
    0.91
     sodass
    0.91
     osob
    0.88
     doen
    0.88
    Activations Density 0.028%

    No Known Activations